Provided are a dialogue device, a dialogue method, a data structure, and a program capable of realizing various dialogues while reducing the amount of description of a dialogue scenario.A knowledge transition unit 120 determines a next type of knowledge based on: a knowledge base 130 in which a relation label indicating each of relations between a plurality of types of knowledge is attached to knowledge about each of utterances to express the knowledge about the utterance; a user utterance; current knowledge; and a dialogue scenario including a basic scenario in which a transition method between the plurality of types of knowledge in the knowledge base is determined using the relation label, and an utterance generation unit 150 generates a system utterance based on the next type of knowledge.
Legal claims defining the scope of protection, as filed with the USPTO.
4. The computer-implemented method of claim 3, wherein the user scenario includes content of the input utterance as a first node, content of the output utterance a second node in response to the input utterance, and a predefined rule for selecting the user scenario, and wherein the user scenario includes a node identifier for specifying a third node in the user scenario to transfer from the first node.
5. The computer-implemented method of claim 3, wherein the knowledge base is a source of information for the output utterance, wherein the dialogue scenario determines a dialogue strategy based at least on the basic scenario or the user scenario, and the knowledge base being distinct from the dialogue scenario.
7. The computer-implemented method of claim 6, wherein the basic scenario includes a first description of how to transition from a type of knowledge to another type of knowledge, and wherein the user scenario includes a second description of how to transition from the input utterance to the output utterance.
11. The system of claim 10, wherein the user scenario includes content of the input utterance as a first node, content of the output utterance a second node in response to the input utterance, and a predefined rule for selecting the user scenario, and wherein the user scenario includes a node identifier for specifying a third node in the user scenario to transfer from the first node.
12. The system of claim 10, wherein the knowledge base is a source of information for the output utterance, wherein the dialogue scenario determines a dialogue strategy based at least on the basic scenario or the user scenario, and the knowledge base being distinct from the dialogue scenario.
14. The system of claim 13, wherein the basic scenario includes a first description of how to transition from a type of knowledge to another type of knowledge, and wherein the user scenario includes a second description of how to transition from the input utterance to the output utterance.
18. The computer-readable non-transitory recording medium of claim 17, wherein the user scenario includes content of the input utterance as a first node, content of the output utterance a second node in response to the input utterance, and a predefined rule for selecting the user scenario, and wherein the user scenario includes a node identifier for specifying a third node in the user scenario to transfer from the first node.
19. The computer-readable non-transitory recording medium of claim 17, wherein the knowledge base is a source of information for the output utterance, wherein the dialogue scenario determines a dialogue strategy based at least on the basic scenario or the user scenario, and the knowledge base being distinct from the dialogue scenario.
Cooperative Patent Classification codes for this invention. Click any code to explore related patents in that topic.
March 4, 2019
January 3, 2023
Browse 5M+ US patents with plain-English claim translations and AI-generated analysis.